Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    formal style instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ne
    1.83
     Lo
    1.71
     Jo
    1.67
    Ne
    1.59
     Su
    1.58
     Se
    1.57
     Fo
    1.56
     Er
    1.54
     Fi
    1.53
     ge
    1.53
    POSITIVE LOGITS
    Hara
    1.07
     consentimiento
    1.04
    Butyl
    1.04
     facultad
    1.00
     bahagia
    1.00
     asignatura
    1.00
     acque
    0.99
     dulces
    0.98
     departamentos
    0.97
     voda
    0.96
    Act Density 0.296%

    No Known Activations